{"mean_reward": 264.36270752113103, "std_reward": 12.230896750138076, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-26T16:54:55.814873"} |
{"mean_reward": 264.36270752113103, "std_reward": 12.230896750138076, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-08-26T16:54:55.814873"} |